Sammenlign metoder
Gennemgå dine valgte metoder side om side; rækker, der afviger, er fremhævet.
| Online læring× | Selvovervåget læring× | |
|---|---|---|
| Fagområde | Maskinlæring | Maskinlæring |
| Familie | Machine learning | Machine learning |
| Oprindelsesår≠ | 1958–2000s | 2018–2020 |
| Ophavsperson≠ | Rosenblatt, F.; Littlestone, N.; Shalev-Shwartz, S. (key contributors) | LeCun, Y. and community (formalized ~2018–2020) |
| Type≠ | Learning paradigm (sequential model update) | Representation learning paradigm |
| Oprindelig kilde≠ | Shalev-Shwartz, S. (2011). Online Learning and Online Convex Optimization. Foundations and Trends in Machine Learning, 4(2), 107–194. DOI ↗ | LeCun, Y. & Misra, I. (2022). Self-supervised learning: The dark matter of intelligence. Meta AI Blog. https://ai.facebook.com/blog/self-supervised-learning-the-dark-matter-of-intelligence/ link ↗ |
| Aliasser | incremental learning, sequential learning, streaming learning, online machine learning | SSL, self-supervised pre-training, pretext-task learning, unsupervised representation learning |
| Relaterede≠ | 6 | 3 |
| Resumé≠ | Online learning is a machine learning paradigm in which a model is updated incrementally as each new data point arrives, rather than being trained once on a fixed dataset. It is essential when data streams continuously, storage is limited, or the underlying distribution shifts over time. Theoretical performance is measured by cumulative regret relative to the best fixed predictor in hindsight. | Self-supervised learning (SSL) is a machine-learning paradigm that generates its own supervisory signal directly from unlabeled data by defining an auxiliary pretext task — such as predicting masked words, rotating images, or contrasting augmented views — and uses the learned representations as a powerful starting point for downstream tasks with minimal labeled examples. |
| ScholarGateDatasæt ↗ |
|
|